4 papers
Cross-Lingual Exploration for Parametric Knowledge
Elisha Diskind, Itamar Trainin, Uri Shaham +3
Parametric knowledge in Large Language Models is not equally accessible across languages. As a result, standard inference techniques often struggle to surface localized facts, lead…
The Shape of Testimony: A Scalable Framework for Oral History Archive Comparison
Itamar Trainin, Renana Keydar, Amit Pinchevski
Researchers in Holocaust studies have often distinguished between two styles of oral survivor testimony: the USC Shoah Foundation's interviews tend to follow a structured, intervie…
Discrete Diffusion Models Exploit Asymmetry to Solve Lookahead Planning Tasks
Itamar Trainin, Shauli Ravfogel, Omri Abend +1
While Autoregressive (AR) Transformer-based Generative Language Models are frequently employed for lookahead tasks, recent research suggests a potential discrepancy in their abilit…
: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Sets
Itamar Trainin, Omri Abend
Using LLMs for Multi-Document Topic Extraction has recently gained popularity due to their apparent high-quality outputs, expressiveness, and ease of use. However, most existing ev…